A hybrid electricity price forecasting model for the Nordic electricity spot market

作者：Voronin Sergey^*; Partanen Jarmo; Kauranne Tuomo

来源：International Transactions on Electrical Energy Systems, 2014, 24(5): 736-760.

DOI：10.1002/etep.1734

• electricity price forecast
• price spikes
• ARMA
• GARCH
• neural network
• Gaussian mixture
• model
• K-nearest neighboring

A hybrid electricity price forecasting model for the Finnish electricity spot market is proposed. The daily electricity price time series is analyzed in two layers - normal behavior and spiky behavior. Two different data preprocessing techniques are applied to handle trend and seasonality in the time series. An ARMA-based model is used to catch the linear relationship between the normal range price series and the explanatory variable, a GARCH model is used to unveil the heteroscedastic character of residuals and a neural network is applied to present the nonlinear impact of the explanatory variable on electricity prices and improve predictions based on time series techniques. The probability of a price spike occurrence and the value of a price spike are produced by a Gaussian Mixture model and K-nearest neighboring model, respectively. Forecasts of normal range prices and price spikes are generated to form an overall price forecast up to one week ahead. The results show that hybridization of the normal range price and price spikes forecasts may provide comprehensive and valuable information for electricity market participants.

• 出版日期2014-5